Skip to Main Content
The exponential growth of the publicly available data has transformed biology into an information rich science that provides new and interesting applications for the machine learning community. In this article, the author presents some specific examples regarding the possibility of representing biological data in a machine-learning framework as well as the contributions these representations impart to both the prediction and discovery of the biological function. The paper also illustrates the proper feature selection critical to the success of the of a particular computational functional genomics approach.
Date of Publication: Nov. 2004